AI Engineer World's Fair 2026
Talks from AI Engineer World's Fair 2026, drafted from the AI Engineer channel's own playlists. Editorial metadata is best-effort parsed and under review.
Event 1
-
226 ↓9
Agentic Security: Permissions, Provenance, and the Agent Supply Chain — Steve Yegge, Gas Town
3.2K views 56 likes 6 comments
-
227 ↓7
First Steps Toward Automated AI Research — Richard Socher, CEO Recursive AI
3.1K views 59 likes 4 comments
-
228 ↓9
From Signal to PR: Anatomy of a Self-Improving Agent — Jason Lopatecki, Arize
3.1K views 54 likes 4 comments
-
229 ↓11
How AI Agents Let GTM Teams Scale — Justin Joyce, Cloudflare
3.1K views 18 likes 2 comments
-
230 ↓9
Every Solo Agent Builder Eventually Reinvents a Worse Version of CI/CD - Sumaiya Shrabony
3.1K views 50 likes 5 comments
-
231 ↓9
Scaling up Continual Learning — Ronak Malde, Trajectory
3.1K views 72 likes 3 comments
-
232 ↓9
The Prompt Is Still a Punch Card - Ted Johnson, JoinIn AI
2.9K views 55 likes 3 comments
-
233 ↓9
Teaching AI to Find Real Vulnerabilities — Prof. David Brumley, Bugcrowd
2.9K views 58 likes 4 comments
-
234 ↓9
Realtime multiplayer, automation, and you! — Idan Gazit, GitHub
2.8K views 32 likes 6 comments
-
235 ↓9
Stop Writing Tone Instructions. Layer Them. - Isadora Martin-Dye, Isadora & Co
2.8K views 59 likes 5 comments
-
236 ↓9
Security Firewall for Agents — Ryan Dahl, Deno
2.8K views 87 likes 7 comments
-
237 ↓8
Rethinking Environments for Long-Horizon Work — Rayan Garg, Theta Software
2.8K views 47 likes 5 comments
-
238 ↓10
The Missing Layer After Launch - Raphael Kalandadze, Wandero AI
2.7K views 55 likes 12 comments
-
239 ↓8
The Miranda Hypothesis: How Hamilton Poisoned Persona Evals - Jacob E. Thomas, Results Gen
2.7K views 23 likes 0 comments
-
240 ↓8
The AI bugpocalypse is here. Now what? - Jack Cable, Corridor
2.6K views 40 likes 3 comments
-
241 ↓11
Always-on agents run production without the on-call tax — Justin Smith, Resolve AI
2.6K views 13 likes 3 comments
-
242 ↓9
How Web Data Infrastructure Powers the Next Generation of AI — Patricija Žemaitytė, Oxylabs
2.5K views 29 likes 4 comments
-
243 ↓9
How Evals and Prompts Shape Agent Behavior — Preetika Bhateja & Daniel Bump, YouTube Ads
2.5K views 42 likes 0 comments
-
244 ↓9
I Run a Fleet of AI Agents Across Three Machines. Here's What Broke. - Kyle Jaejun Lee, KRAFTON
2.5K views 72 likes 8 comments
-
245 ↓9
The Messy Reality of Scale: Synthetic Data and Pre-Training — Marah Abdin & Robert McHardy, poolside
2.5K views 48 likes 3 comments
-
246 ↓9
Agents in Production: How OpenGov Built and Scaled OG Assist - Gabe De Mesa, OpenGov
2.5K views 65 likes 0 comments
-
247 ↓9
From Blind Spots to Merged PRs: Continuous Agentic Performance Optimization - May Walter, Hud
2.4K views 82 likes 0 comments
-
248 ↓6
Emulated: The Data for Fully Autonomous Software Engineers and Companies — Joseph Wang
2.4K views 28 likes 0 comments
-
249 ↓10
Structuring the Unstructured - Cedric Clyburn, Red Hat
2.4K views 82 likes 4 comments
-
250 ↓10
Beyond Static Intelligence: Evaluating Continual Learning — Parth Asawa, UC Berkeley
2.3K views 50 likes 1 comments
